© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78778
    Prev
    Next
    INDEX
    Explanations

    selected value or index

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects use of the dot-access operator in code (e.g. object.property, especially accessing `.value`).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     become
    -0.91
    Xc
    -0.78
    𖥻
    -0.77
    开始
    -0.76
    要不要
    -0.75
    énom
    -0.74
     福岡
    -0.74
     des
    -0.74
     神戸
    -0.73
    niest
    -0.71
    POSITIVE LOGITS
    SelectedItem
    0.96
     selected
    0.95
    选中
    0.95
    selectedItem
    0.92
    selectedIndex
    0.89
    getSelected
    0.86
    setSelected
    0.85
     pierres
    0.78
    SelectedValue
    0.77
    蓮
    0.77
    Activations Density 0.009%

    No Known Activations